© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 14109
    Prev
    Next
    INDEX
    Explanations

    phrases that have to do with reputation or negative impressions

    oai_token-act-pair · gemini-2.0-flash

    reputation, embarrassment

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     صوتيه
    -0.87
     Roskov
    -0.68
    +#+#
    -0.66
     виправивши
    -0.66
    }$​
    -0.57
    KURZBESCHREIBUNG
    -0.57
     Normdatei
    -0.56
    propTypes
    -0.56
    lwjgl
    -0.56
     transférez
    -0.56
    POSITIVE LOGITS
    complexType
    0.54
    Spoljašnje
    0.49
     embarrassment
    0.48
     visitors
    0.46
     significant
    0.45
    InSection
    0.45
    tomic
    0.44
     pubblic
    0.44
     branding
    0.44
     bogotá
    0.43
    Activations Density 0.353%

    No Known Activations