© 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-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 13052
    Prev
    Next
    INDEX
    Explanations

    apple varieties

    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_13_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
    </code>
    0.50
     agr
    0.46
     easy
    0.45
    easy
    0.43
    ad
    0.43
    self
    0.43
    </h3>
    0.42
    zinger
    0.42
    вед
    0.41
    gon
    0.41
    POSITIVE LOGITS
     thawed
    0.57
     thawing
    0.56
     холоди
    0.55
    ඖ
    0.54
     Bento
    0.52
     pdelay
    0.52
     zdjęcia
    0.52
    Refrigerator
    0.52
     Нью
    0.51
    ɨ
    0.50
    Activations Density 0.034%

    No Known Activations