INDEX

Explanations

newline characters and the characters that immediately proceed them

oai_token-act-pair · gemini-2.0-flash

n

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Akismet

-0.50

 pageable

-0.49

AnimationsModule

-0.49

OrNil

-0.47

AtIndexPath

-0.46

евна

-0.45

 chisel

-0.45

Naissance

-0.44

flickr

-0.44

 Perseus

-0.44

POSITIVE LOGITS

تقاوى

0.84

WebVitals

0.64

rungsseite

0.64

帖最后由

0.61

 snippetHide

0.60

audiovisuel

0.55

حوالہ

0.54

 sekali

0.54

enterOuterAlt

0.54

 heard

0.50

Activations Density 3.214%

newline characters and the characters that immediately proceed them

n

No Comments

No Known Activations