© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 593
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to actions one can take.

    oai_token-act-pair · gemini-2.0-flash

    Filler words/prepositions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    AndEndTag
    -1.02
     Houſe
    -0.74
     ་་
    -0.73
    principalTable
    -0.73
     ―――――
    -0.71
     nakalista
    -0.71
    __":
    -0.70
    .")
    -0.68
    })`
    -0.68
    .”—
    -0.66
    POSITIVE LOGITS
     your
    1.16
     the
    1.09
     this
    0.99
     you
    0.98
     him
    0.98
     them
    0.91
     it
    0.91
     these
    0.87
     his
    0.87
     our
    0.86
    Activations Density 17.857%

    No Known Activations