© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 6148
    Prev
    Next
    INDEX
    Explanations

    the substring "Sal"

    oai_token-act-pair · gemini-2.0-flash

    Sal

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    Geplaatst
    -0.89
     resourceCulture
    -0.83
     itſelf
    -0.77
    fromnode
    -0.74
    +#+
    -0.73
    yntaxException
    -0.73
     Roskov
    -0.73
     ModelExpression
    -0.71
    localctx
    -0.70
     themſelves
    -0.70
    POSITIVE LOGITS
     Mull
    0.40
    Sum
    0.40
     face
    0.39
     sum
    0.37
     mão
    0.35
     Sum
    0.35
     mặt
    0.34
     Mang
    0.34
     t
    0.33
    aman
    0.33
    Activations Density 0.580%

    No Known Activations