© 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. 8729
    Prev
    Next
    INDEX
    Explanations

    sentences that evaluate something

    oai_token-act-pair · gemini-2.0-flash

    just

    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
    pure
    -0.66
     pure
    -0.63
    PURE
    -0.59
    '])
    -0.59
    UnitTesting
    -0.56
    }));
    -0.55
    \}\\
    -0.54
     pura
    -0.54
     PURE
    -0.54
    ']))
    -0.53
    POSITIVE LOGITS
     fubject
    0.68
     ſtate
    0.67
     ſeveral
    0.67
     myſelf
    0.67
     houſe
    0.64
     Majefty
    0.63
     qed
    0.60
     whoſe
    0.60
     Suivez
    0.60
     juſ
    0.60
    Activations Density 14.539%

    No Known Activations