© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 89258
    Prev
    Next
    INDEX
    Explanations

    model

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_60_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
    ̸
    0.42
     ni
    0.40
     достой
    0.39
    TN
    0.38
    shad
    0.38
     વર્
    0.38
    etí
    0.38
    }//
    0.36
    uzzo
    0.36
     midd
    0.35
    POSITIVE LOGITS
     Hight
    0.46
    </td>
    0.43
    ელს
    0.39
     Excited
    0.37
    শিক্ষ
    0.36
     అందుకే
    0.36
     Listening
    0.35
     factor
    0.35
     dugo
    0.35
    羮
    0.35
    Activations Density 0.164%

    No Known Activations