INDEX

Explanations

numeric strings or short phrases with numbers

oai_token-act-pair · gemini-2.0-flash

specific numerical values or identifiers

np_token-act-pair-logits · gpt-4o-mini

single-digit numbers

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

Билгалдахарш

-0.79

 للمعارف

-0.77

 Италијани

-0.69

 initComponents

-0.68

 utafitiHapana

-0.66

estacks

-0.65

 HasFactory

-0.64

httphttps

-0.61

 unknownFields

-0.60

 Wicidata

-0.60

POSITIVE LOGITS

″]

0.57

0.50

ha

0.46

gar

0.44

Datuak

0.44

hub

0.44

0.43

 Star

0.43

Activations Density 16.056%

numeric strings or short phrases with numbers

specific numerical values or identifiers

single-digit numbers

No Comments

No Known Activations