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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 6186
    Prev
    Next
    INDEX
    Explanations

    sentences talking about research and collaboration

    oai_token-act-pair · gemini-2.0-flash

    Academic papers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    SourceChecksum
    -0.98
    مصادر
    -0.89
     Roskov
    -0.84
    tagHelperRunner
    -0.81
    expandindo
    -0.80
    ⓧ
    -0.77
     nahilalakip
    -0.77
    complexContent
    -0.73
    PyExc
    -0.72
    rungsseite
    -0.71
    POSITIVE LOGITS
     Jef
    0.44
    WHEREAS
    0.44
    tvguidetime
    0.44
    Included
    0.42
    AccessorTable
    0.41
    Jeografia
    0.40
    ("")]
    0.40
    krankungen
    0.39
    SuppressWarnings
    0.38
     ne
    0.38
    Activations Density 0.951%

    No Known Activations