© 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. 134558
    Prev
    Next
    INDEX
    Explanations

    novels

    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
    ä
    1.00
    U
    0.92
     damper
    0.90
    ü
    0.89
    ı
    0.88
    ividual
    0.86
    дин
    0.85
    ла
    0.84
    V
    0.84
    ᇁ
    0.81
    POSITIVE LOGITS
    2
    1.09
     I
    0.93
    ts
    0.80
    })
    0.79
    ط
    0.79
    am
    0.77
    য়া
    0.77
    জ
    0.77
    ال
    0.77
    סים
    0.76
    Activations Density 0.000%

    No Known Activations