© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 83005
    Prev
    Next
    INDEX
    Explanations

    filter list

    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_29_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
     forbade
    0.42
    IMENTS
    0.41
    借
    0.41
     食
    0.40
     Exactly
    0.40
    リュー
    0.39
     forbids
    0.39
    तिहासिक
    0.38
    luk
    0.38
    Exactly
    0.37
    POSITIVE LOGITS
     medizin
    0.38
     экономической
    0.37
     медицин
    0.36
     medically
    0.36
     Chatter
    0.36
    versorgung
    0.34
    需
    0.34
    post
    0.33
     hardening
    0.33
    anc
    0.32
    Activations Density 0.004%

    No Known Activations