© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 30885
    Prev
    Next
    INDEX
    Explanations

    states are

    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_31_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
     possesses
    0.40
     possess
    0.39
     ec
    0.38
     di
    0.37
    `(
    0.36
     fon
    0.36
     sahip
    0.36
     poss
    0.35
    ਝ
    0.35
     deprec
    0.35
    POSITIVE LOGITS
     appointees
    0.39
     제한
    0.38
     बढ़ने
    0.38
    morale
    0.38
     কমে
    0.37
    ୈ
    0.36
    的生活
    0.36
     अधी
    0.36
     외
    0.35
     डियर
    0.35
    Activations Density 0.052%

    No Known Activations