© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 204502
    Prev
    Next
    INDEX
    Explanations

    G g

    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_56_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
    ﻰ
    0.38
     s
    0.38
     oxides
    0.37
    心态
    0.37
    ryt
    0.37
    тивным
    0.36
    oxides
    0.36
    платы
    0.36
    탠
    0.36
    exon
    0.35
    POSITIVE LOGITS
    redients
    0.41
     translate
    0.40
    transl
    0.39
    ameth
    0.38
    StringEncoding
    0.37
    支
    0.37
    copper
    0.36
     Mack
    0.36
     conference
    0.35
    িয়োগ
    0.35
    Activations Density 0.000%

    No Known Activations