© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 6-GEMMASCOPE-TRANSCODER-16K
    7. 14282
    Prev
    Next
    INDEX
    Explanations

    words related to statements of belief, interspersed with a short amount of vulgar sexual content, and some programming language imports

    oai_token-act-pair · gemini-2.0-flash

    sexually explicit, repetition

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    "])
    -0.56
     EconPapers
    -0.54
    ]})
    -0.53
    χρι
    -0.51
     ausz
    -0.51
    )}</
    -0.48
    ,:),
    -0.48
     respectivamente
    -0.48
    memberOf
    -0.47
    ']).
    -0.47
    POSITIVE LOGITS
    rungsseite
    0.80
     neceff
    0.67
     miſ
    0.59
     houſe
    0.55
     ſtand
    0.55
     conmigo
    0.54
     purpoſe
    0.54
     ſte
    0.53
     ſub
    0.53
     anſ
    0.53
    Activations Density 42.957%

    No Known Activations