INDEX

Explanations

the letter "k" or "K."

oai_token-act-pair · gemini-2.0-flash

k

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

ThroughAttribute

-0.81

featureID

-0.70

 relâche

-0.69

afficheront

-0.68

LookAnd

-0.68

HtmlAttribute

-0.66

Tikang

-0.66

IUrlHelper

-0.66

bewerken

-0.65

 JpaRepository

-0.65

POSITIVE LOGITS

selves

0.48

andidat

0.48

AxisAlignment

0.46

حياته

0.44

achts

0.42

ser

0.42

 zich

0.42

IELD

0.41

avier

0.41

son

0.41

Activations Density 4.474%

the letter "k" or "K."

k

No Comments

No Known Activations