INDEX

Explanations

the word "seat"

oai_token-act-pair · gemini-2.0-flash

seat

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

 seat

-3.13

seat

-2.66

 Seat

-2.64

Seat

-2.52

 seats

-2.44

 Seats

-2.16

 SEAT

-2.09

seats

-2.03

Seats

-1.84

 seating

-1.69

POSITIVE LOGITS

 lenker

0.57

OGND

0.55

الدراسه

0.50

 المعيارى

0.50

 بيها

0.50

sodik

0.49

 GenerationType

0.49

ValueStyle

0.48

 favoritas

0.48

 solucion

0.47

Activations Density 1.455%

the word "seat"

seat

No Comments

No Known Activations