© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 2828
    Prev
    Next
    INDEX
    Explanations

    IP, CLIP, hip, mip

    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_39_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
    Arbit
    0.39
    Favor
    0.38
     sortir
    0.37
     Arbit
    0.37
     Favor
    0.37
    раста
    0.36
    usehen
    0.35
    疋
    0.35
    erald
    0.34
    یکن
    0.34
    POSITIVE LOGITS
    cip
    0.46
     Cip
    0.46
     आईपी
    0.46
    IPT
    0.45
     HIP
    0.45
    mip
    0.45
     Kip
    0.44
     ips
    0.44
    hip
    0.43
    Mip
    0.43
    Activations Density 0.092%

    No Known Activations