© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 15890
    Prev
    Next
    INDEX
    Explanations

    the word "spa" and words related to claims.

    oai_token-act-pair · gemini-2.0-flash

    Spas and representations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    bootstrapcdn
    -0.66
    sellor
    -0.65
    cinated
    -0.63
    agramm
    -0.62
     становника
    -0.62
     Freedman
    -0.61
     La
    -0.60
    oscope
    -0.60
     Nak
    -0.60
     N
    -0.59
    POSITIVE LOGITS
     purpoſe
    1.08
     ſtate
    0.87
     neceff
    0.86
     uſe
    0.84
     ſeveral
    0.83
     ſame
    0.82
     Diſ
    0.82
     inſ
    0.80
     Majefty
    0.80
     fometimes
    0.80
    Activations Density 0.893%

    No Known Activations