© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 139031
    Prev
    Next
    INDEX
    Explanations

    review article

    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_12_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
    I
    0.45
    Begin
    0.44
    AY
    0.41
    Here
    0.41
    AM
    0.41
    ING
    0.40
    OK
    0.39
    C
    0.38
    There
    0.38
    here
    0.37
    POSITIVE LOGITS
     MILLER
    0.41
     бо
    0.40
     decap
    0.40
     conceded
    0.39
     allocated
    0.38
     oversaw
    0.38
     quantify
    0.38
     conceding
    0.38
     vínculo
    0.38
    ний
    0.37
    Activations Density 0.000%

    No Known Activations