© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 14587
    Prev
    Next
    INDEX
    Explanations

    snippets of javascript code with some Portuguese.

    oai_token-act-pair · gemini-2.0-flash

    code and other languages

    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
    ]--;
    -0.60
    )++;
    -0.58
    AndEndTag
    -0.54
    $}}
    -0.53
    -};
    -0.53
    })));
    -0.53
     disambiguazione
    -0.52
     cherchés
    -0.52
    :]:
    -0.51
    }}]{
    -0.51
    POSITIVE LOGITS
     démocr
    0.36
     nationaux
    0.35
     alemanes
    0.35
     chré
    0.35
     judicia
    0.34
     africains
    0.34
     industriels
    0.34
     vocales
    0.33
     faibles
    0.33
     Juifs
    0.33
    Activations Density 9.967%

    No Known Activations