© 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. 206593
    Prev
    Next
    INDEX
    Explanations

    (ACL, MCL, LCL, PCL) abbreviations

    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
    ।
    1.15
    }
    1.08
    {
    1.06
    N
    1.05
    )
    1.00
    3
    0.94
    Des
    0.93
    '
    0.90
    =-
    0.89
    Calc
    0.86
    POSITIVE LOGITS
    il
    0.99
    ુ
    0.97
    하는
    0.93
    ure
    0.93
    ul
    0.92
    tty
    0.88
    ną
    0.86
    ivasena
    0.86
    to
    0.85
    нето
    0.85
    Activations Density 0.000%

    No Known Activations