© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 232070
    Prev
    Next
    INDEX
    Explanations

    Respuesta sarcástica, Residenz, Respuesta a

    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_6_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
    2
    0.96
     Aeonium
    0.90
    zeitig
    0.86
    pros
    0.84
    bner
    0.82
    reihe
    0.82
     Pří
    0.81
    zón
    0.80
     Gora
    0.80
    ান
    0.80
    POSITIVE LOGITS
    in
    1.46
    on
    1.30
     on
    1.24
    ی
    1.16
    ens
    1.05
    다
    1.05
    ong
    0.94
     virtualization
    0.90
    ח
    0.89
    ५
    0.89
    Activations Density 0.002%

    No Known Activations