© 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. 133852
    Prev
    Next
    INDEX
    Explanations

    pinhead

    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
    бо
    1.02
    ين
    0.84
    كار
    0.82
     شكل
    0.81
    غ
    0.80
    де
    0.80
    การ
    0.79
    то
    0.78
     utilisent
    0.78
     récemment
    0.77
    POSITIVE LOGITS
    ac
    0.81
    Amazing
    0.75
    ia
    0.73
    Logout
    0.73
    Login
    0.69
    Lamp
    0.68
    Termination
    0.67
    Guardian
    0.67
    that
    0.66
    <h1>
    0.65
    Activations Density 0.000%

    No Known Activations