© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 39561
    Prev
    Next
    INDEX
    Explanations

    word endings

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_57_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
     f
    2.89
     ف
    2.13
    f
    2.03
    ｆ
    2.00
     ф
    1.87
    ฟ
    1.79
    𝑓
    1.73
     फ
    1.60
    <0x86>
    1.59
    𝒇
    1.55
    POSITIVE LOGITS
     DI
    0.40
    erved
    0.36
     HI
    0.36
    риз
    0.36
     SI
    0.34
     RI
    0.34
    డవ
    0.34
    antiate
    0.34
    nance
    0.33
    bros
    0.33
    Activations Density 0.256%

    No Known Activations