INDEX

Explanations

words of subjective evaluation and the discussion of objective facts.

oai_token-act-pair · gemini-2.0-flash

Proper nouns

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

 Normdatei

-1.04

ftagPool

-1.01

 ComVisible

-0.99

WriteTagHelper

-0.99

WebVitals

-0.94

 defaultstate

-0.94

 AssemblyCulture

-0.93

protoimpl

-0.91

 CreateTagHelper

-0.90

LookAnd

-0.90

POSITIVE LOGITS

 amyloid

0.75

 Conspiracy

0.73

 Virat

0.72

 Reels

0.71

 Evita

0.71

 Silvio

0.70

 Cerebral

0.70

 Priscilla

0.70

 Britney

0.70

 Sauvignon

0.69

Activations Density 92.880%

words of subjective evaluation and the discussion of objective facts.

Proper nouns

No Comments

No Known Activations