© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 60287
    Prev
    Next
    INDEX
    Explanations

    oakland

    np_acts-logits-general · gemini-2.5-flash-lite

    Oak

    np_max-act · claude-4-5-haikuTriggered by @enricobottazzi

    proper nouns, particularly place names and well-known character or entity names.

    oai_token-act-pair · claude-4-5-haikuTriggered by @enricobottazzi

    words starting with O

    np_max-act-logits · claude-4-5-haikuTriggered by @enricobottazzi
    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
    ്
    1.20
    z
    1.05
     consecut
    1.02
    ﻭ
    1.02
    ş
    1.00
     центром
    0.96
    (
    0.93
    ബരിമല
    0.93
    ত
    0.93
    ને
    0.92
    POSITIVE LOGITS
     on
    1.44
    am
    1.41
     an
    1.33
    i
    1.27
    ند
    1.15
     you
    1.13
    if
    1.13
    ：
    1.11
    0
    1.10
    you
    1.08
    Activations Density 0.000%

    No Known Activations