INDEX

Explanations

words related to fantasy games and combat.

oai_token-act-pair · gemini-2.0-flash

Monsters and villains

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

RegistryLite

-0.69

complexContent

-0.69

ItemBackground

-0.67

FundMe

-0.66

monster

-0.66

 Italij

-0.66

SourceChecksum

-0.63

 Appraisal

-0.62

 monster

-0.61

 Signalez

-0.60

POSITIVE LOGITS

ⓧ

0.44

ods

0.43

ood

0.43

 điều

0.42

Cac

0.42

zk

0.40

áz

0.39

wur

0.39

OCCURRED

0.39

Activations Density 4.496%

words related to fantasy games and combat.

Monsters and villains

No Comments

No Known Activations