© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 193676
    Prev
    Next
    INDEX
    Explanations

    customer review or specific names

    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_4_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
    t
    1.04
    to
    0.80
    us
    0.62
    ش
    0.61
    以
    0.61
    al
    0.59
     metab
    0.59
    א
    0.59
    的核心
    0.58
    及
    0.58
    POSITIVE LOGITS
    про
    0.77
    }
    0.73
    ]
    0.68
    вла
    0.67
    ک
    0.66
    ]$
    0.66
    па
    0.65
     हादसे
    0.64
    missione
    0.64
    начала
    0.63
    Activations Density 0.000%

    No Known Activations