INDEX

Explanations

mentions of rankings or scores

oai_token-act-pair · gemini-2.0-flash

rankings

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 rankings

-0.88

 ranking

-0.79

 Rankings

-0.75

IntoConstraints

-0.70

ranking

-0.68

 Ranking

-0.68

 ranked

-0.65

rank

-0.64

 rank

-0.63

RANK

-0.62

POSITIVE LOGITS

лтемелер

0.63

Посилання

0.57

 estimés

0.52

 AssemblyTitle

0.51

getSupport

0.49

Tazama

0.48

 Chwiliwch

0.48

脚注の使い方

0.46

 getItemId

0.46

tahui

0.46

Activations Density 12.245%

mentions of rankings or scores

rankings

No Comments

No Known Activations