Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 23-GEMMASCOPE-TRANSCODER-16K
    4. 12050
    Prev
    Next
    INDEX
    Explanations

    javascript code

    oai_token-act-pair · gemini-2.0-flash

    Code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     or
    -0.55
     e
    -0.55
     her
    -0.53
     he
    -0.53
     i
    -0.52
     and
    -0.52
     so
    -0.50
     self
    -0.50
     per
    -0.50
     ve
    -0.49
    POSITIVE LOGITS
     Monfieur
    0.98
     ModelExpression
    0.93
     ſche
    0.89
    ⓧ
    0.86
     Theſe
    0.84
     myſelf
    0.81
     purpoſe
    0.80
     незавершена
    0.79
     pleaſure
    0.79
     Eſ
    0.78
    Activations Density 14.413%

    No Known Activations