© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 13574
    Prev
    Next
    INDEX
    Explanations

    statements of fact or opinion in legal, scientific, or political writing.

    oai_token-act-pair · gemini-2.0-flash

    conclusions or agreements

    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
    ьаж
    -0.74
    StoryboardSegue
    -0.69
     tartalomajánló
    -0.68
     yaiba
    -0.66
    oredCriteria
    -0.66
     kaarangay
    -0.65
    paccio
    -0.65
    Хьажоргаш
    -0.63
    }),
    -0.61
    featureID
    -0.61
    POSITIVE LOGITS
    KommentareTeilen
    0.71
     that
    0.50
     AspNetCore
    0.48
     cref
    0.46
     اطلع
    0.44
     –
    0.44
     he
    0.42
     Empieza
    0.42
    Identyfik
    0.41
    ngOnInit
    0.40
    Activations Density 0.845%

    No Known Activations