INDEX

Explanations

text related to character stats and abilities from the game World of Warcraft

oai_token-act-pair · gemini-2.0-flash

Code and documentation

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

 EconPapers

-0.85

цездатний

-0.61

ObjectContext

-0.60

 Audiodateien

-0.59

 مشين

-0.57

dirond

-0.56

EndProject

-0.55

Brainz

-0.54

 gynhyrchwyd

-0.52

queryInterface

-0.51

POSITIVE LOGITS

WriteAttribute

0.65

ValueStyle

0.52

دانشنامهٔ

0.50

 onCreateView

0.47

Παραπομπές

0.47

ckså

0.45

GRANTED

0.45

 cottura

0.45

TestingModule

0.45

EDEFAULT

0.44

Activations Density 2.908%

text related to character stats and abilities from the game World of Warcraft

Code and documentation

No Comments

No Known Activations