© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 170938
    Prev
    Next
    INDEX
    Explanations

    cam/camp

    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
     tá
    0.53
     та
    0.45
    },-
    0.35
    боре
    0.35
    タ
    0.35
    utum
    0.34
    ustat
    0.34
    ocot
    0.34
     tas
    0.34
    㙂
    0.34
    POSITIVE LOGITS
     kam
    1.38
     câ
    1.32
    c
    1.32
     cams
    1.23
    C
    1.21
    ค
    1.20
     ла
    1.18
     cam
    1.16
    Kam
    1.13
     CAM
    1.09
    Activations Density 0.009%

    No Known Activations