© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 3074
    Prev
    Next
    INDEX
    Explanations

    code snippets containing abbreviated code and numbers.

    oai_token-act-pair · gemini-2.0-flash

    snippets from different sources

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     req
    -1.02
     Dir
    -0.98
     Gov
    -0.98
    req
    -0.96
     Elem
    -0.94
     Eq
    -0.94
    Req
    -0.93
     proj
    -0.93
     Req
    -0.91
     Eqs
    -0.91
    POSITIVE LOGITS
    Portale
    0.59
    mybatisplus
    0.48
     XG
    0.45
     RMA
    0.45
     '-':
    0.44
    Viitteet
    0.42
     Româ
    0.40
     '+':
    0.40
     '{}
    0.40
    わけです
    0.39
    Activations Density 4.115%

    No Known Activations