© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 4073
    Prev
    Next
    INDEX
    Explanations

    strings of special characters and/or numbers and/or capitalized letters

    oai_token-act-pair · gemini-2.0-flash

    Turkish language/references

    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
     estekak
    -0.69
    헌
    -0.56
    +#+#
    -0.55
     كومونز
    -0.51
    __':
    -0.49
    AsUp
    -0.49
    //
    -0.48
    الإنجليزية
    -0.47
    رشف
    -0.46
    __":
    -0.45
    POSITIVE LOGITS
    ktör
    0.52
    nsic
    0.49
    hahn
    0.48
    klü
    0.48
     vă
    0.48
    zle
    0.48
    ğaz
    0.48
    PLICATE
    0.48
    şit
    0.47
    sendStatus
    0.47
    Activations Density 1.644%

    No Known Activations