INDEX

Explanations

words about limitations or restrictions

oai_token-act-pair · gemini-2.0-flash

limiting/confining

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

تقاوى

-0.61

Personendaten

-0.60

 Numerade

-0.60

ngdoc

-0.59

 ollut

-0.56

EndGlobalSection

-0.55

tellten

-0.54

 lätt

-0.53

matchCondition

-0.52

かります

-0.52

POSITIVE LOGITS

unggu

0.63

 solely

0.57

Tyl

0.57

 only

0.56

Tyl

0.54

>[]

0.54

 primarily

0.53

 mainly

0.53

 sını

0.52

 Hanya

0.51

Activations Density 2.362%

words about limitations or restrictions

limiting/confining

No Comments

No Known Activations