© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 214919
    Prev
    Next
    INDEX
    Explanations

    Howey Test, scam, teaching, inaturalist

    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_5_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
     différent
    1.09
    ٥
    1.09
    ٦
    1.06
    は
    1.05
     saddened
    1.03
    తో
    1.00
    是
    1.00
    ೭
    1.00
    కు
    0.98
    łoży
    0.96
    POSITIVE LOGITS
    v
    1.71
    x
    1.52
    m
    1.41
    j
    1.29
    t
    1.19
    et
    1.14
    inin
    1.11
    q
    1.07
     as
    1.05
    ari
    1.05
    Activations Density 0.000%

    No Known Activations