© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 232333
    Prev
    Next
    INDEX
    Explanations

    therapists

    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
     clase
    0.88
     molte
    0.88
     laugh
    0.85
     nouvelle
    0.85
     precedence
    0.82
    ᄊ
    0.82
     chocolat
    0.81
     scoff
    0.81
     fend
    0.79
     Bereich
    0.79
    POSITIVE LOGITS
    un
    1.32
    س
    1.27
    ع
    1.26
    ok
    1.21
    ح
    1.20
    ur
    1.13
    ח
    1.11
    as
    1.09
    ang
    1.09
    ir
    1.08
    Activations Density 0.000%

    No Known Activations