INDEX

Explanations

language describing the mechanics of a machine

oai_token-act-pair · gemini-2.0-flash

foreign language

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

WebVitals

-0.63

 SafeMath

-0.60

 ModelExpression

-0.57

 pitié

-0.56

modelBuilder

-0.56

HCM

-0.56

 صوتيه

-0.55

addCriterion

-0.55

kháu

-0.55

 дописавши

-0.54

POSITIVE LOGITS

ángulo

0.49

んぼ

0.47

rítica

0.47

 scouring

0.45

 glancing

0.44

 DRAWINGS

0.44

ioe

0.43

ariously

0.43

ingly

0.43

 apron

0.43

Activations Density 11.238%

language describing the mechanics of a machine

foreign language

No Comments

No Known Activations