INDEX

Explanations

occurrences of religious, folklore, or spiritual contexts.

oai_token-act-pair · gemini-2.0-flash

the

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

Efq

-0.73

 purpoſe

-0.72

 Theſe

-0.66

 itſelf

-0.63

 dreamstime

-0.63

neſs

-0.63

 >=",

-0.60

 détermination

-0.60

 متعلقه

-0.59

wiſe

-0.59

POSITIVE LOGITS

complexContent

0.56

SystemColors

0.49

 חיצוניים

0.46

di

0.45

ClientSize

0.42

ftagPool

0.41

 gyhoeddwyd

0.41

けている

0.40

 visual

0.40

lo

0.39

Activations Density 4.004%

occurrences of religious, folklore, or spiritual contexts.

the

No Comments

No Known Activations