© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 18-GEMMASCOPE-TRANSCODER-16K
    7. 6931
    Prev
    Next
    INDEX
    Explanations

    parenthetical phrases, especially those with numeric or scientific content

    oai_token-act-pair · gemini-2.0-flash

    Code/definitions/lists

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/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.18.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
    AsUp
    -1.29
    Personendaten
    -1.22
    __":
    -1.19
     noDo
    -1.14
    enumi
    -1.12
    LookAnd
    -1.07
    __':
    -1.02
     كومونز
    -1.02
     pinulongan
    -0.98
     Normdatei
    -0.97
    POSITIVE LOGITS
    -
    0.93
    ·
    0.77
     -
    0.60
    h
    0.57
    -(
    0.55
    (
    0.55
     s
    0.54
     S
    0.52
    -,
    0.52
    x
    0.51
    Activations Density 1.720%

    No Known Activations