© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 10395
    Prev
    Next
    INDEX
    Explanations

    the pronouns "her," "their," and references to ownership or location.

    oai_token-act-pair · gemini-2.0-flash

    terms related to residences or living spaces

    np_token-act-pair-logits · gpt-4o-mini

    residences

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AndEndTag
    -0.73
     autorytatywna
    -0.61
    LookAnd
    -0.60
    AnimationsModule
    -0.56
    migrationBuilder
    -0.56
     beina
    -0.55
     صوتيه
    -0.53
    awtextra
    -0.52
    InitVars
    -0.52
    Билгалдахарш
    -0.52
    POSITIVE LOGITS
     living
    0.98
     residences
    0.91
    living
    0.88
     residence
    0.82
     residential
    0.76
    Living
    0.76
     Living
    0.75
     Residences
    0.75
     homes
    0.72
     birth
    0.72
    Activations Density 2.376%

    No Known Activations