© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 89071
    Prev
    Next
    INDEX
    Explanations

    date restrictions before release

    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_23_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
    ration
    0.51
    rad
    0.45
    na
    0.44
     ration
    0.42
    ness
    0.41
    nor
    0.41
    r
    0.41
    ini
    0.41
    aro
    0.40
    CM
    0.40
    POSITIVE LOGITS
     économiques
    0.47
    হাব
    0.42
    䏹
    0.42
    yspace
    0.41
    热爱
    0.41
     actuel
    0.41
     Smack
    0.41
     alps
    0.40
     Colombeau
    0.40
    ക്കിയത്
    0.40
    Activations Density 0.000%

    No Known Activations