© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 63632
    Prev
    Next
    INDEX
    Explanations

    team members

    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_59_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
    M
    1.13
     M
    0.46
     મ
    0.41
     MDS
    0.39
    Gun
    0.39
     MBS
    0.38
     MIP
    0.37
    ಮ
    0.37
    ouver
    0.36
    ਾਮ
    0.36
    POSITIVE LOGITS
     Member
    1.77
     Members
    1.52
    Member
    1.20
     MEMBER
    0.79
    Members
    0.74
     मेंबर
    0.63
     MEMBERS
    0.61
     Membership
    0.58
    会员
    0.55
    MemberList
    0.50
    Activations Density 0.021%

    No Known Activations