© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11394
    Prev
    Next
    INDEX
    Explanations

    sequences of articles, prepositions, and numbers

    oai_token-act-pair · gemini-2.0-flash

    technical terms and proper nouns

    np_token-act-pair-logits · gpt-4o-mini

    Historical/legal/political texts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     صوتيه
    -0.61
     HasFactory
    -0.58
    sitivity
    -0.52
     cytometry
    -0.51
    ktar
    -0.51
    esteld
    -0.49
    iance
    -0.47
     Deletion
    -0.47
     soprav
    -0.47
    AnchorStyles
    -0.46
    POSITIVE LOGITS
    HostException
    0.76
     Efq
    0.56
    getMenuInflater
    0.56
     Cæsar
    0.54
    VersionUID
    0.54
    washer
    0.52
     Frenchmen
    0.52
     hindurch
    0.52
    airro
    0.51
    chables
    0.51
    Activations Density 1.817%

    No Known Activations