© 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. 14658
    Prev
    Next
    INDEX
    Explanations

    arabic characters and numerals

    oai_token-act-pair · gemini-2.0-flash

    mixed content/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
     تانيه
    -0.76
     resourceCulture
    -0.75
     للمعارف
    -0.58
     fieldNum
    -0.57
    Personensuche
    -0.57
    fjspx
    -0.57
     متعلقه
    -0.53
     يتيمه
    -0.52
     مرئيه
    -0.52
    #+#
    -0.51
    POSITIVE LOGITS
    وافق
    0.69
    خلص
    0.60
    راجع
    0.57
    ضمن
    0.57
    >{"
    0.56
    جموع
    0.52
    شارك
    0.51
    ختلف
    0.50
    وزيع
    0.48
    ÍO
    0.47
    Activations Density 0.739%

    No Known Activations