© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 11280
    Prev
    Next
    INDEX
    Explanations

    phrases describing a process progressing or changing, often for the worse

    oai_token-act-pair · gemini-2.0-flash

    Something goes wrong

    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
    UnusedPrivate
    -0.95
     дописавши
    -0.83
    
    -0.78
    Diweddarwch
    -0.77
    principalTable
    -0.77
     defaultstate
    -0.76
     tartalomajánló
    -0.75
     समीक्षाओं
    -0.73
    adaptiveStyles
    -0.72
    AsUp
    -0.72
    POSITIVE LOGITS
    ApiRequest
    0.50
    lar
    0.49
    ahkan
    0.47
    VIR
    0.46
     Marion
    0.45
     TAYLOR
    0.45
    ävän
    0.44
    MENAFN
    0.44
     devront
    0.44
    unków
    0.43
    Activations Density 7.611%

    No Known Activations