INDEX

Explanations

mathematical formulas and statistical surveys

oai_token-act-pair · gemini-2.0-flash

code, math symbols

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

IndentedString

-0.81

SourceChecksum

-0.76

 betweenstory

-0.72

PreferredItem

-0.65

ReusableCell

-0.61

localctx

-0.60

LLocation

-0.60

stdc

-0.59

tagHelperRunner

-0.58

addCriterion

-0.57

POSITIVE LOGITS

وروبا

0.57

 igenom

0.55

 kysy

0.49

 commerciaux

0.48

accio

0.48

 répé

0.48

 vägen

0.48

ミナル

0.47

 kohta

0.47

 gräns

0.46

Activations Density 32.142%

mathematical formulas and statistical surveys

code, math symbols

No Comments

No Known Activations