© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 35215
    Prev
    Next
    INDEX
    Explanations

    Hair removal

    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_3_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
     be
    0.75
     de
    0.70
     (
    0.65
     IPM
    0.58
     IPA
    0.57
     ICA
    0.57
     إ
    0.57
     FA
    0.57
    am
    0.56
     IBA
    0.56
    POSITIVE LOGITS
    3
    0.77
    분에
    0.65
    i
    0.63
    인
    0.63
    COLUMN
    0.61
    간
    0.61
    AUTHENT
    0.61
    لی
    0.60
    য়োজন
    0.60
    カロ
    0.60
    Activations Density 0.002%

    No Known Activations