© 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. 1034
    Prev
    Next
    INDEX
    Explanations

    the number 1 and metadata like section headers and equation symbols

    oai_token-act-pair · gemini-2.0-flash

    1

    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
    
    -0.52
     "..\..\..\
    -0.49
    AsUp
    -0.47
     дописавши
    -0.45
     Савезне
    -0.45
     समीक्षाओं
    -0.44
    <bos>
    -0.43
    ngths
    -0.42
    zzleHttp
    -0.42
    urably
    -0.42
    POSITIVE LOGITS
    /}
    0.60
    </b>
    0.60
    }$\
    0.59
    AutoSize
    0.58
     发表于
    0.58
    GroupLayout
    0.57
     std
    0.57
     }
    0.57
     /*
    0.56
     };
    0.56
    Activations Density 14.120%

    No Known Activations