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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11498
    Prev
    Next
    INDEX
    Explanations

    Java code and package declarations

    oai_token-act-pair · gemini-2.0-flash

    programming language syntax

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

    period

    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
     T
    -0.86
     
    -0.84
     U
    -0.80
     a
    -0.79
     O
    -0.77
     R
    -0.74
     V
    -0.73
     I
    -0.73
     the
    -0.71
     Z
    -0.71
    POSITIVE LOGITS
     itſelf
    1.34
     كومونز
    1.19
     myſelf
    1.13
     Efq
    1.10
     Theſe
    1.09
     raiſ
    1.06
     تانيه
    1.04
    tvguidetime
    1.03
     houſe
    1.00
     Normdatei
    0.98
    Activations Density 4.017%

    No Known Activations