INDEX

Explanations

phrases indicating direction or extent

oai_token-act-pair · gemini-2.0-flash

distance/movement

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 AssemblyTitle

-0.54

 Franken

-0.46

юз

-0.46

日発売

-0.46

 imper

-0.46

URLException

-0.45

olol

-0.44

itets

-0.44

she

-0.43

 Rates

-0.42

POSITIVE LOGITS

 AssemblyCulture

0.75

migrationBuilder

0.74

 оригіналу

0.65

 consultato

0.60

 reaching

0.60

 onPage

0.59

DataURL

0.59

Reach

0.59

reached

0.59

χρι

0.58

Activations Density 1.558%

phrases indicating direction or extent

distance/movement

No Comments

No Known Activations