© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 11896
    Prev
    Next
    INDEX
    Explanations

    places where a user is describing technical options and alternatives

    oai_token-act-pair · gemini-2.0-flash

    alternatives or services

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     betweenstory
    -1.17
    fjspx
    -1.12
     beginnetje
    -0.91
     Мексичка
    -0.87
    InjectAttribute
    -0.82
    DockStyle
    -0.81
     незавершена
    -0.76
    ValueStyle
    -0.75
    sizeCache
    -0.72
    verwijspagina
    -0.72
    POSITIVE LOGITS
     Reverso
    0.56
    draw
    0.46
     couver
    0.46
     GILBERT
    0.44
     resourceCulture
    0.44
     بيها
    0.44
    otimes
    0.43
    ir
    0.43
     πυ
    0.43
     خل
    0.43
    Activations Density 0.676%

    No Known Activations