© 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. 7316
    Prev
    Next
    INDEX
    Explanations

    adverbs, especially "sometimes," followed by words describing states of being or actions.

    oai_token-act-pair · gemini-2.0-flash

    sometimes

    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
     always
    -1.04
    always
    -0.89
     Always
    -0.84
     sempre
    -0.84
    sempre
    -0.83
     sometimes
    -0.83
    Always
    -0.82
     ALWAYS
    -0.78
    sometimes
    -0.76
    awsze
    -0.75
    POSITIVE LOGITS
     Normdatei
    0.49
    modo
    0.49
    uzzy
    0.48
    Massa
    0.47
    ichteten
    0.46
    rechter
    0.46
    ródło
    0.45
    head
    0.45
    engager
    0.45
    GeneratedMessage
    0.45
    Activations Density 9.463%

    No Known Activations