INDEX

Explanations

numbers and symbols related to measurements and degrees

oai_token-act-pair · gemini-2.0-flash

single digit numbers

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

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

indor

-0.59

 jScrollPane

-0.57

+#+

-0.56

 ErrIntOverflow

-0.54

Jeografia

-0.54

 للاسماء

-0.53

AndEndTag

-0.52

 Administrativna

-0.52

RRect

-0.52

/**

-0.51

POSITIVE LOGITS

1.43

1.41

1.37

1.35

1.34

1.33

1.31

1.02

Activations Density 35.531%

numbers and symbols related to measurements and degrees

single digit numbers

No Comments

No Known Activations