© 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-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 8960
    Prev
    Next
    INDEX
    Explanations

    Island Skiff

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-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
    Negative Logits
    ज
    0.62
     τραγ
    0.57
    ering
    0.56
    াম
    0.55
    }^*
    0.53
    }+\
    0.52
     playa
    0.52
    ({\
    0.51
    |)
    0.51
    ity
    0.51
    POSITIVE LOGITS
    gegevens
    0.65
     싶은
    0.65
     Gegensatz
    0.63
    нансо
    0.63
     setzte
    0.62
     Gedanken
    0.61
    bygg
    0.61
    sekut
    0.60
     setzt
    0.59
    ই
    0.58
    Activations Density 0.000%

    No Known Activations