© 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. 6019
    Prev
    Next
    INDEX
    Explanations

    sentences with multiple instances of particular words; it highlights different kinds of specialized and academic language that contain repeated short words such as "of", "the", "in", and "to", often in conjunction with longer, content-rich words from a variety of domains.

    oai_token-act-pair · gemini-2.0-flash

    negative traits

    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
    '},
    -0.84
    .)}
    -0.78
    ")));
    -0.71
    "},
    -0.71
     */}
    -0.69
    "];
    -0.68
    ')));
    -0.68
    }*/
    -0.67
    )]
    -0.66
    '],
    -0.66
    POSITIVE LOGITS
     defamation
    0.76
     claust
    0.74
     Aggression
    0.73
     incest
    0.72
     irony
    0.69
     impartiality
    0.69
     bragging
    0.69
     Enforcement
    0.68
     arrogance
    0.68
     hypocrisy
    0.68
    Activations Density 19.832%

    No Known Activations