© 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. 13626
    Prev
    Next
    INDEX
    Explanations

    code snippets or logic that refer to conditional "if/then" type statements, especially in programming languages

    oai_token-act-pair · gemini-2.0-flash

    future tense verbs

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

    words meaning "should"

    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
     pleaſure
    -0.74
     Majefty
    -0.66
    ſelf
    -0.65
     houſe
    -0.64
    Portale
    -0.63
     ſeveral
    -0.61
     itſelf
    -0.61
     poffe
    -0.60
     ſche
    -0.60
     myſelf
    -0.60
    POSITIVE LOGITS
     shall
    1.74
    shall
    1.48
     SHALL
    1.29
     Shall
    1.23
    Shall
    1.08
     be
    0.88
     legyen
    0.78
     skal
    0.75
     soit
    0.74
     soient
    0.73
    Activations Density 0.811%

    No Known Activations