© 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. 14687
    Prev
    Next
    INDEX
    Explanations

    phrases commonly preceding an explanation as to the reason for something, especially when "that is required" is part of the phrase.

    oai_token-act-pair · gemini-2.0-flash

    legal/academic writing

    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
    MigrationBuilder
    -0.60
    }?>
    -0.57
    setVerticalGroup
    -0.56
     defaultstate
    -0.54
    MarshalTo
    -0.53
    ()}>
    -0.51
    ://$
    -0.51
    GTCX
    -0.50
     AssemblyCompany
    -0.49
    :]:
    -0.49
    POSITIVE LOGITS
    tvguidetime
    0.66
    ArgsConstructor
    0.64
    ResumeLayout
    0.56
     lenker
    0.52
    ticolo
    0.50
    
    0.50
    ⓧ
    0.50
    InstanceState
    0.49
    orated
    0.49
    Aiheesta
    0.48
    Activations Density 1.020%

    No Known Activations