© 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. 45092
    Prev
    Next
    INDEX
    Explanations

    digitalocean, grain, approximation

    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
    ৬৮
    0.43
    VCTarget
    0.42
    zg
    0.42
     مذہ
    0.41
    LOTRE
    0.41
    ㎎
    0.41
     ግን
    0.39
     Postgraduate
    0.39
    zp
    0.39
    бычно
    0.39
    POSITIVE LOGITS
     h
    0.38
     forklift
    0.37
     blew
    0.37
     allocate
    0.36
     rotated
    0.36
    ی
    0.36
     tail
    0.36
    un
    0.36
     hvert
    0.35
     separating
    0.35
    Activations Density 0.007%

    No Known Activations