© 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
    2. Gemma-3-27B-IT
    3. 6-GEMMASCOPE-2-TRANSCODER-262K
    4. 132663
    Prev
    Next
    INDEX
    Explanations

    magazines and organizers

    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_6_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
     on
    1.45
    ’
    1.38
    is
    1.19
    '
    1.18
     gym
    1.13
     
    1.13
     $
    1.09
    .
    1.05
     limpia
    1.02
     board
    1.00
    POSITIVE LOGITS
    }";
    1.31
     Ичиго
    1.20
    <unused1938>
    1.20
     Балтбет
    1.16
    <unused475>
    1.16
    txtbtn
    1.13
    \"");
    1.13
    К
    1.13
     overruled
    1.09
    "+"|".
    1.09
    Activations Density 0.004%

    No Known Activations