© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 2492
    Prev
    Next
    INDEX
    Explanations

    citations, references, and context switching between conversational turns in a question-answer format.

    oai_token-act-pair · gemini-2.0-flash

    E

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    rungsseite
    -0.61
     насељу
    -0.61
    Życiorys
    -0.59
     Drapeau
    -0.48
    зок
    -0.47
    /***/
    -0.46
     INTERESAR
    -0.46
    chengladbach
    -0.46
    fromnode
    -0.45
    :+:
    -0.45
    POSITIVE LOGITS
     E
    2.66
    E
    2.36
    Ｅ
    1.50
     Е
    1.48
    getE
    1.48
     Э
    1.23
     Eo
    1.20
     É
    1.19
    Е
    1.17
     ई
    1.16
    Activations Density 7.376%

    No Known Activations