© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 121243
    Prev
    Next
    INDEX
    Explanations

    good intentions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_27_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
     correcta
    0.36
     économ
    0.34
     ఊ
    0.34
     Cast
    0.33
     Lyrics
    0.32
     şark
    0.32
     CPM
    0.31
     Aut
    0.31
     ત
    0.31
     Polit
    0.31
    POSITIVE LOGITS
    aidl
    0.39
    plural
    0.35
    動作
    0.35
    借助
    0.33
    ceed
    0.32
    atih
    0.32
     abgesch
    0.32
    เนิน
    0.32
    电源
    0.32
    Grouping
    0.32
    Activations Density 0.006%

    No Known Activations