© 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-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 3924
    Prev
    Next
    INDEX
    Explanations

    a mix of first-person pronouns, action verbs, and words related to software or hardware interaction.

    oai_token-act-pair · gemini-2.0-flash

    releasing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyTitle
    -0.88
    setVerticalGroup
    -0.85
    tvguidetime
    -0.76
    Hentet
    -0.76
    OGND
    -0.75
     للمعارف
    -0.73
     Aquila
    -0.70
    PreferredItem
    -0.69
     المعيارى
    -0.69
     calendriers
    -0.69
    POSITIVE LOGITS
     release
    1.66
     released
    1.51
    release
    1.43
    Release
    1.41
     Release
    1.40
     freeing
    1.38
     releases
    1.36
     frees
    1.35
     freed
    1.34
     releasing
    1.33
    Activations Density 1.685%

    No Known Activations