INDEX

Explanations

mentions of trails, tours, and generally navigating places.

oai_token-act-pair · gemini-2.0-flash

tours and exploring

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

ורך

-0.54

ühm

-0.50

ngdoc

-0.48

britanni

-0.47

avadoc

-0.47

 enfer

-0.47

 mérit

-0.46

 RouterModule

-0.45

ʲ

-0.45

ctid

-0.45

POSITIVE LOGITS

Lähteet

0.77

Trama

0.66

 Wiktionnaire

0.62

脚注の使い方

0.61

 Roskov

0.60

FunctionFlags

0.59

nî

0.56

Rptr

0.54

 AttributeSet

0.54

 nawr

0.53

Activations Density 1.629%

mentions of trails, tours, and generally navigating places.

tours and exploring

No Comments

No Known Activations

mentions of trails, tours, and generally navigating places.

tours and exploring

No Comments

No Known Activations