© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 12357
    Prev
    Next
    INDEX
    Explanations

    words related to effects, influences, and impacts.

    oai_token-act-pair · gemini-2.0-flash

    influence

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     effects
    -1.20
     effect
    -1.17
    effects
    -1.16
    effect
    -1.14
     Effects
    -1.12
     impact
    -1.11
    Effects
    -1.09
    impact
    -1.09
    Impact
    -1.07
     Effect
    -1.05
    POSITIVE LOGITS
    <bos>
    0.57
     rosse
    0.49
     türlü
    0.47
     ويكيميديا
    0.46
    sendStatus
    0.45
     CHAPITRE
    0.44
    unnitel
    0.43
     Cassini
    0.43
    Pairing
    0.42
     perhatian
    0.42
    Activations Density 34.599%

    No Known Activations