© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 8276
    Prev
    Next
    INDEX
    Explanations

    phrases involving the termination of an event

    oai_token-act-pair · gemini-2.0-flash

    occurrences of "end"

    np_token-act-pair-logits · gpt-4o-mini

    end

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     end
    -0.98
    End
    -0.85
     End
    -0.84
    end
    -0.81
     END
    -0.73
     SEDS
    -0.66
    Ends
    -0.65
    末
    -0.64
    END
    -0.63
     einde
    -0.63
    POSITIVE LOGITS
     of
    0.96
    PullParser
    0.63
    stående
    0.57
    tymologie
    0.57
    ummer
    0.55
     của
    0.53
    \{\\
    0.51
     eorum
    0.50
     quæ
    0.49
    alike
    0.49
    Activations Density 3.088%

    No Known Activations