© 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-3-27B-IT
    5. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 83252
    Prev
    Next
    INDEX
    Explanations

    belief or beliefs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_0_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    t
    1.70
    ре
    1.59
    l
    1.48
    h
    1.46
    い
    1.45
    lr
    1.41
    las
    1.40
    lj
    1.38
    v
    1.37
    lx
    1.33
    POSITIVE LOGITS
    ;
    1.55
    '
    1.48
     in
    1.45
     of
    1.40
     la
    1.33
    >
    1.31
     (
    1.27
     envoy
    1.26
     individ
    1.22
    ார்
    1.21
    Activations Density 0.004%

    No Known Activations