© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 7801
    Prev
    Next
    INDEX
    Explanations

    words used to express feelings or opinions, especially negative ones, as well as intensifiers and words related to difficulty or effort.

    oai_token-act-pair · gemini-2.0-flash

    Very

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
     myſelf
    -0.89
     itſelf
    -0.80
     Houſe
    -0.78
     Majefty
    -0.77
    ſelf
    -0.77
    esterday
    -0.77
     мәкал
    -0.77
     themſelves
    -0.76
    __':
    -0.76
     himſelf
    -0.75
    POSITIVE LOGITS
     very
    1.89
     Very
    1.59
    Very
    1.52
     VERY
    1.52
    very
    1.52
     extremely
    1.52
     très
    1.36
     muy
    1.31
     sangat
    1.30
    VERY
    1.29
    Activations Density 0.833%

    No Known Activations