© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 153
    Prev
    Next
    INDEX
    Explanations

    code related to configuration of software

    oai_token-act-pair · gemini-2.0-flash

    code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    ::
    -1.66
     :
    -1.47
     ::
    -1.46
    :
    -1.33
    :::
    -1.22
     :-
    -1.19
    :-
    -1.16
    ,:
    -1.12
    :(
    -1.10
    :/
    -1.08
    POSITIVE LOGITS
     تانيه
    0.64
     rhestr
    0.57
     Himo
    0.55
     numberOfRows
    0.54
     onOptions
    0.53
    下载附件
    0.52
    quiel
    0.51
    iecie
    0.50
    oiseau
    0.50
     незавершена
    0.50
    Activations Density 1.420%

    No Known Activations