© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 112486
    Prev
    Next
    INDEX
    Explanations

    affiliation, affidavit, affix, affinity, affirm, affection, affiliate

    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_2_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
    '
    2.09
    er
    1.19
     was
    1.18
    \
    1.17
     be
    1.15
    (
    1.13
    )
    1.10
    सी
    1.04
    :
    1.04
    ів
    1.01
    POSITIVE LOGITS
    ند
    1.56
    }.
    1.28
    ه
    1.27
    red
    1.17
    }"
    1.16
     powied
    1.15
    नं
    1.15
    ש
    1.14
    ."
    1.13
    }",
    1.13
    Activations Density 0.002%

    No Known Activations