© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 121255
    Prev
    Next
    INDEX
    Explanations

    aiming for neutrality

    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_27_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
    isenberg
    0.42
    optimize
    0.42
    bar
    0.41
    opi
    0.40
     vaše
    0.38
     Optimize
    0.37
    follower
    0.37
    Ľ
    0.37
    <h6>
    0.37
    Il
    0.37
    POSITIVE LOGITS
     fairly
    0.37
     неда
    0.35
     ආර
    0.35
     దశ
    0.34
     cru
    0.34
     ज्वाला
    0.33
     आविष्कार
    0.33
    각
    0.33
    たい
    0.33
    ในการ
    0.33
    Activations Density 0.016%

    No Known Activations