INDEX

Explanations

names of companies and institutions

oai_token-act-pair · gemini-2.0-flash

Names in news articles

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

 pygame

-0.66

 sceptre

-0.65

ſelf

-0.59

 skechers

-0.57

 avenger

-0.57

ſelves

-0.56

astify

-0.56

ALR

-0.54

 wlan

-0.54

 Longman

-0.54

POSITIVE LOGITS

findpost

0.74

UrlResolution

0.70

########.

0.67

 EconPapers

0.67

 CreateTagHelper

0.60

StoreMessageInfo

0.58

MigrationBuilder

0.58

ifrance

0.57

paravant

0.56

دانشنامهٔ

0.56

Activations Density 0.874%

names of companies and institutions

Names in news articles

No Comments

No Known Activations