© 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. 6214
    Prev
    Next
    INDEX
    Explanations

    phrases consisting of several words that express subjective evaluation and judgement

    oai_token-act-pair · gemini-2.0-flash

    technical/research documents

    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
    béco
    -0.21
     hö
    -0.19
    Õ
    -0.18
     са
    -0.18
    fl
    -0.18
    esez
    -0.17
    fi
    -0.17
    CA
    -0.16
     се
    -0.16
     Se
    -0.15
    POSITIVE LOGITS
     RSSSF
    1.13
     extrapolated
    1.05
     Jurí
    1.05
    SEGUIR
    1.03
     Gorb
    1.02
     perpetuity
    1.02
     abiye
    1.02
     downvoted
    1.02
     desorption
    1.02
    amaño
    1.01
    Activations Density 71.824%

    No Known Activations