© 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. 1212
    Prev
    Next
    INDEX
    Explanations

    strong recommendations

    oai_token-act-pair · gemini-2.0-flash

    Recommendations and suggestions

    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
     long
    -2.20
    long
    -1.77
    Long
    -1.40
     LONG
    -1.36
     Long
    -1.29
    LONG
    -1.18
     longa
    -1.09
     longterm
    -1.04
     lange
    -1.03
     долго
    -0.99
    POSITIVE LOGITS
    +:+
    0.77
    ########.
    0.69
     propOrder
    0.66
     <<<<<<<<<<<<<<
    0.66
    enumi
    0.64
    enumii
    0.64
    قایناقلار
    0.62
     Numerade
    0.62
    ChildIndex
    0.61
     célèbres
    0.59
    Activations Density 2.001%

    No Known Activations