© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 38476
    Prev
    Next
    INDEX
    Explanations

    data identifiers

    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
    Eds
    0.38
     JC
    0.36
     vă
    0.36
     Anth
    0.33
     overseeing
    0.33
    }^{*}-
    0.33
     HBO
    0.33
    الحكم
    0.33
    HBO
    0.33
    ('#
    0.33
    POSITIVE LOGITS
     groupId
    0.39
    INEN
    0.37
     jabatan
    0.37
    OWER
    0.36
    ignal
    0.36
     കട
    0.35
     Schnee
    0.34
     rien
    0.34
    地方
    0.34
    ullah
    0.34
    Activations Density 0.001%

    No Known Activations