INDEX

Explanations

verbs related to searching, finding, investigation, and observation

oai_token-act-pair · gemini-2.0-flash

searching

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

imb

-0.60

HideFlags

-0.56

RectangleBorder

-0.53

styleType

-0.52

Bru

-0.51

 Holl

-0.51

 surge

-0.50

 Circ

-0.50

HttpEntity

-0.50

円

-0.50

POSITIVE LOGITS

 }}"></

0.58

 GeoNames

0.58

 Ogni

0.57

URLException

0.57

DeleteBehavior

0.56

 nido

0.55

 îna

0.52

 Piscina

0.52

 تضيفلها

0.52

DebuggerNonUser

0.52

Activations Density 2.112%

verbs related to searching, finding, investigation, and observation

searching

No Comments

No Known Activations