INDEX

Explanations

the letter "C" in various contexts

oai_token-act-pair · gemini-2.0-flash

C

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

 للاسماء

-0.93

StoryboardSegue

-0.86

 AssemblyProduct

-0.78

Personensuche

-0.78

 bezeichneter

-0.77

цездатний

-0.77

 Administrativna

-0.74

AndEndTag

-0.74

 kaarangay

-0.71



-0.70

POSITIVE LOGITS

uyler

0.56

ENSUS

0.54

ENSIS

0.52

ANCY

0.51

tist

0.48

IBLE

0.47

istry

0.47

IMUM

0.46

IGHT

0.46

ITATION

0.46

Activations Density 4.823%

the letter "C" in various contexts

C

No Comments

No Known Activations