© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 258813
    Prev
    Next
    INDEX
    Explanations

    numbers, prices, percentages

    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_22_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
     ți
    0.54
    ANCES
    0.52
    année
    0.49
     lọ
    0.48
     þei
    0.48
    Ą
    0.47
     कोले
    0.47
     proprie
    0.46
    gados
    0.46
     biennium
    0.46
    POSITIVE LOGITS
    }$
    0.44
     Leitung
    0.42
     Land
    0.42
     Car
    0.41
    ॥
    0.41
     $+$
    0.40
    чик
    0.40
    id
    0.40
     Hydraulic
    0.40
    <0x0D>
    0.39
    Activations Density 0.000%

    No Known Activations