© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 137210
    Prev
    Next
    INDEX
    Explanations

    which, who, kot

    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_12_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
    ာ
    0.58
    iii
    0.52
    p
    0.51
    ί
    0.51
    itabbam
    0.50
    দর
    0.49
    赔
    0.49
     கர்ப்ப
    0.48
     ආර
    0.48
    if
    0.47
    POSITIVE LOGITS
    }(\
    0.61
    Y
    0.61
    WARD
    0.59
     lesquels
    0.57
     которого
    0.57
     которых
    0.57
    Detach
    0.56
    )。
    0.55
     vilka
    0.55
    }.
    0.54
    Activations Density 0.000%

    No Known Activations