© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 86914
    Prev
    Next
    INDEX
    Explanations

    asset tracking and management

    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_3_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
     \
    0.78
     psychosis
    0.61
     Effekt
    0.60
    钬
    0.60
     Blackmore
    0.59
    anna
    0.59
    อ
    0.57
     Negative
    0.55
     eukaryotic
    0.55
    än
    0.54
    POSITIVE LOGITS
    T
    0.80
    S
    0.77
    P
    0.77
    D
    0.77
    ка
    0.76
    C
    0.76
    ১
    0.76
    O
    0.73
    E
    0.73
    U
    0.71
    Activations Density 0.022%

    No Known Activations